Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection

Liu, Jiang; Levine, Alexander; Lau, Chun Pong; Chellappa, Rama; Feizi, Soheil

doi:10.1109/cvpr52688.2022.01455

Cited by 47 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al 31 suggested an effective adversarial attack strategy for several kinds of object identification models. Liu et al 32 generated an adversarial patch that targets object detection networks and simultaneously attacks the bounding box regression and object classification. In the object segmentation domain, Arnab et al 14 conducted a research study to examine the robustness of different object segmentation models in the face of adversarial examples.…”

Section: Adversarial Attacksmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial attack on human pose estimation network

Zhang,

Huang,

Liu

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Real-time human pose estimation (HPE) using convolutional neural networks (CNN) is critical for enabling machines to better understand human beings based on images and videos, and for assisting supervisors in identifying human behavior. However, CNN-based systems are susceptible to adversarial attacks, and the attacks specifically targeting HPE have received little attention. We present a gradient-based adversarial example generation method, named AdaptiveFool, which is designed to effectively perform a keypoints-invisible attack against OpenPose by aggregating the loss function of human keypoints and generating adaptive adversarial perturbations. In addition, we introduce an object-oriented perturbation generation method during the AdaptiveFool process to eliminate background perturbations. Our proposed method adapts the adversarial perturbations and generates object-oriented perturbations. On COCO 2017 datasets, our method achieves 6.3% mean average precision on OpenPose. This research provides inspiration for future work on developing efficient and effective adversarial example defense methods for HPE.

show abstract

Section: Adversarial Attacksmentioning

confidence: 99%

“…suggested an effective adversarial attack strategy for several kinds of object identification models. Liu et al 32 . generated an adversarial patch that targets object detection networks and simultaneously attacks the bounding box regression and object classification.…”

Section: Related Workmentioning

confidence: 99%

Adversarial attack on human pose estimation network

Zhang,

Huang,

Liu

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Brown et al (2017) suggested that a neural net can be fooled by completely replacing a part of an image with their designed patch. Liu et al (2019) presented a black-box adversarial patch termed D-PATCH that can simultaneously attack the bounding box regression and object classification. Moreover, Athalye et al (2017) presented expectation over transformation (EOT), a general-purpose algorithm for creating robust adversarial examples that can successfully fabricate three-dimensional adversarial objects.…”

Section: Adversarial Patchmentioning

confidence: 99%

Machine learning and blockchain technologies for cybersecurity in connected vehicles

Ahmad,

Zia,

Naqvi

et al. 2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Future connected and autonomous vehicles (CAVs) must be secured against cyberattacks for their everyday functions on the road so that safety of passengers and vehicles can be ensured. This article presents a holistic review of cybersecurity attacks on sensors and threats regarding multi‐modal sensor fusion. A comprehensive review of cyberattacks on intra‐vehicle and inter‐vehicle communications is presented afterward. Besides the analysis of conventional cybersecurity threats and countermeasures for CAV systems, a detailed review of modern machine learning, federated learning, and blockchain approach is also conducted to safeguard CAVs. Machine learning and data mining‐aided intrusion detection systems and other countermeasures dealing with these challenges are elaborated at the end of the related section. In the last section, research challenges and future directions are identified.This article is categorized under: Commercial, Legal, and Ethical Issues > Security and Privacy Technologies > Machine Learning Technologies > Internet of Things

show abstract

“…presented a patch attack to fool the automated driving systems by modifying the road signs under various conditions. Furthermore, many researchers have evaluated this attack in various applications, such as object detection and FR in digital 36 and physical environments 37 , 38 …”

Section: Literature Surveymentioning

confidence: 99%

M-SAN: a patch-based transferable adversarial attack using the multi-stack adversarial network

Agrawal

Bhatnagar

2023

J. Electron. Imag.

View full text Add to dashboard Cite

In recent times, deep neural networks (DNN) have been extensively used in several areas and have achieved great success. State-of-the-art face recognition (FR) systems have gained high accuracy using DNN. However, researchers have found that DNN-based systems fail when facing an adversarial attack on images. In adversarial attacks, the adversary modifies the face images in a manner that the human does not perceive the changes in the generated image but FR systems are unable to recognize the faces correctly. We proposed a method to generate an adversarial attack. A multistack adversarial network (M-SAN) patch-based attack is generated using the generative adversarial network under the black-box settings. The M-SAN attack targets the features of the face images using a patch to fool the FR model as targeted and untargeted attacks. In the past, several attack generation methods have been presented under white-box settings. However, white-box settings need a model architecture and information about its parameters. Due to this, a single white-box attack is not able to fool different FR models. We propose an attack generation approach that is based on black-box settings in which an attacker does not have access to the target model parameters. The attack is generated with the help of the surrogate model and then transferred to the various target models. The proposed M-SAN attack is applied to FR models including FaceNet, ArcFace, and CosFace on the labeled face in the wild dataset.

show abstract

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection

Cited by 47 publications

References 22 publications

Adversarial attack on human pose estimation network

Adversarial attack on human pose estimation network

Machine learning and blockchain technologies for cybersecurity in connected vehicles

M-SAN: a patch-based transferable adversarial attack using the multi-stack adversarial network

Contact Info

Product

Resources

About